Ahmed Abdelreheem

I am a CS Ph.D. candidate at King Abdullah University of Science and Technology, working under the supervision of Prof. Peter Wonka. My research focuses on the intersection of 3D vision, natural language, and computer graphics, with an emphasis on building models that reason about 3D scenes and objects through language. I am particularly interested in spatial reasoning, object-centric representations, and the use of LLMs and 3D LLMs for 3D understanding and editing.

profile photo
News
25 Jun 2024
I joined Niantic Inc. as a research intern in London.
24 Oct 2023
Our paper is accepted at WACV 2024.
20 Sep 2023
Our paper is accepted at SIGGRAPH Asia 2023.
Education
PhD in Computer Science, KAUST
Thuwal, Saudi Arabia
May 2022 - Present
MS in Computer Science, KAUST
Thuwal, Saudi Arabia
Mar. 2020 - May 2022
BSc in Computer Engineering, Cairo University
Cairo, Egypt
Sep. 2015 - May 2019
Experience
Research Intern, Niantic Inc.
London, UK
Jun. 2024 - Nov. 2024
Research Intern, Snap Inc.
Palo Alto, CA, USA
Jun. 2022 - Oct. 2022
Research Intern, Stanford University
Guibas Laboratory, Remote
Jun. 2021 - Aug. 2021
Publications
Place It 3D
PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes
Ahmed Abdelreheem, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Abdelrahman Eldesokey, Peter Wonka, Gabriel Brostow, Sara Vicente, Guillermo Garcia-Hernando
arXiv preprint
ZeroKey
ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models
Bingchen Gong, Diego Gomez, Abdullah Hamdi, Abdelrahman Eldesokey, Ahmed Abdelreheem, Peter Wonka, Maks Ovsjanikov
arXiv preprint
3DCoMPaT++
3DCoMPaT++: An improved Large-scale 3D Vision Dataset for Compositional Recognition
Habib Slim, Xiang Li, Yuchen Li, Mahmoud Ahmed, Mohamed Ayman, Ujjwal Upadhyay, Ahmed Abdelreheem, Arpit Prajapati, Suhail Pothigara, Peter Wonka, Mohamed Elhoseiny
arXiv preprint
ScanEnts3D
ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes
Ahmed Abdelreheem, Kyle Olszewski, Hsin-Ying Lee, Peter Wonka, Panos Achlioptas
WACV 2024
Zero-Shot 3D Shape Correspondence
Ahmed Abdelreheem, Abdelrahman Eldesokey, Maks Ovsjanikov, Peter Wonka
SIGGRAPH Asia 2023
SATR: Zero-Shot Semantic Segmentation of 3D Shapes
Ahmed Abdelreheem, Ivan Skorokhodov, Maks Ovsjanikov, Peter Wonka
ICCV 2023
3DCoMPaT
3DCoMPaT: Composition of Materials on Parts of 3D Things
Yuchen Li*, Ujjwal Upadhyay*, Habib Slim*, Ahmed Abdelreheem, Arpit Prajapati, Suhail Pothigara, Peter Wonka, Mohamed Elhoseiny
ECCV 2022
(Oral Presentation)
3DRefTransformer
3DRefTransformer: Fine-Grained Object Identification in Real-World Scenes Using Natural Language
Ahmed Abdelreheem, Ujjwal Upadhyay, Ivan Skorokhodov, Rawan Al Yahya, Jun Chen, Mohamed Elhoseiny
WACV 2022
ReferIt3D
ReferIt3D: Neural Listeners for Fine-Grained Object Reference in Real-World 3D Scenes
Panos Achlioptas, Ahmed Abdelreheem, Fei Xia, Mohamed Elhoseiny, Leonidas Guibas
ECCV 2020
(Oral Presentation)
Academic Service
  • Reviewer for CVPR 2024, 2025.
  • Reviewer for 3DV 2024.
  • Reviewer for SIGGRAPH Asia 2023, 2024.
  • Reviewer for SIGGRAPH 2024.
  • Reviewer for ICCV 2023, 2025.
  • Reviewer for ECCV 2024.
  • Reviewer for WACV 2023, 2024.
Teaching Experience
  • Teaching assistant in the "Deep Learning for Visual Computing" course, taught by Prof. Peter Wonka at King Abdullah University of Science and Technology in Fall 2023.
Misc.
  • Top 10 in ACM Sigmod Programming Contest 2021

This template is a modification to Jon Barron's website.